EEDT_DC

The Flanders Make EEDT_DC core lab combines in-depth physical insightsinto electromechanics with insights obtained from data that becomesavailable in today industry 4.0 setting applying state-of-the-art andinnovative artificial intelligence routines (Hybrid AI). As such we contribute to building:

·        Explainable and transferabledigital twins, and 

·        Explainable and trustworthyAI for the manufacturing industry. 

Specific aspects of our research include: 

·        Development of:

o  (multiplicative)hybrid data-physical models for explainable condition monitoring;

o  (multiplicative)hybrid data-physical models for explainable system identification;

o  Probabilistic decision-making routines that are adaptive, explainable andtransferable; 

o  Reinforced learning control enhanced with physics suitablefor the manufacturing industry;

o  Low-probability eventestimations and predictions.

·        Sensing &monitoring of (a fleet of) drivetrains;

·        Control &decision making of (a fleet of) drivetrains;

·        Virtual sensing of electricalmachines based on electrical signal analysis for condition monitoring; 

·        Stochastic and uncertaintymodelling to evaluate and improve the effectiveness of sensing and monitoringstrategies;

·        Camera-based sensing and monitoring of oil film in anddegradation of bearings and gearboxes;  

·        Controller structures thatleverage on the well-known, safe and robust traditional control structuresenhanced with AI to include data driven learnings or (high fidelity) models toimprove performance 

·        Techniques to do automatic(e.g. context aware) PID tuning

·        Distributed optimal controltechniques 

·        Use of AI techniques tocorrelate product-process features